sobjects/textparsers.py
author Julien Jehannet <julien.jehannet@logilab.fr>
Fri, 05 Feb 2010 17:13:53 +0100
changeset 4527 67ab70e98488
parent 4252 6c4f109c2b03
child 5421 8167de96c523
permissions -rw-r--r--
[R] devtools: improve default data import mechanism Validation chain is now possible with checkers Before that the expected values needed to be coherent. Now, we can use ObjectStore to validate the input data * add new input transformers: - uppercase - lowercase * add new input checkers (raise AssertionError on error): - decimal: take care of possible comma character as number separator - integer: cast to int() - yesno: to validate boolean value - isalpha - required: input value *must* not be empty * new control checker: - optional: block possible exception we delete field in the returned dict instead of raising AssertionError (exclusive with required) Helper methods to manipulate indexes: * build_rqlindex() is used to build index based on already created entities * fetch() replace get_one()/get_many() methods by factorizing code Minor changes in reporting: * use tell() for all printing * let new value for askerrors to display automatically the report (used in crontab)

"""hooks triggered on email entities creation:

* look for state change instruction (XXX security)
* set email content as a comment on an entity when comments are supported and
  linking information are found

:organization: Logilab
:copyright: 2003-2010 LOGILAB S.A. (Paris, FRANCE), all rights reserved.
:contact: http://www.logilab.fr/ -- mailto:contact@logilab.fr
"""
__docformat__ = "restructuredtext en"

import re

from cubicweb import UnknownEid, typed_eid
from cubicweb.view import Component

        # XXX use user session if gpg signature validated

class TextAnalyzer(Component):
    """analyze and extract information from plain text by calling registered
    text parsers
    """
    __regid__ = 'textanalyzer'

    def parse(self, caller, text):
        for parsercls in self._cw.vreg['components'].get('textparser', ()):
            parsercls(self._cw).parse(caller, text)


class TextParser(Component):
    """base class for text parser, responsible to extract some information
    from plain text. When something is done, it usually call the

      .fire_event(something, {event args})

    method on the caller.
    """
    __regid__ = 'textparser'
    __abstract__ = True

    def parse(self, caller, text):
        raise NotImplementedError


class ChangeStateTextParser(TextParser):
    """search some text for change state instruction in the form

         :<transition name>: #?<eid>
    """
    instr_rgx = re.compile(':(\w+):\s*#?(\d+)', re.U)

    def parse(self, caller, text):
        for trname, eid in self.instr_rgx.findall(text):
            try:
                entity = self._cw.entity_from_eid(typed_eid(eid))
            except UnknownEid:
                self.error("can't get entity with eid %s", eid)
                continue
            if not hasattr(entity, 'in_state'):
                self.error('bad change state instruction for eid %s', eid)
                continue
            tr = entity.current_workflow and entity.current_workflow.transition_by_name(trname)
            if tr and tr.may_be_fired(entity.eid):
                try:
                    trinfo = entity.fire_transition(tr)
                    caller.fire_event('state-changed', {'trinfo': trinfo,
                                                        'entity': entity})
                except:
                    self.exception('while changing state of %s', entity)
            else:
                self.error("can't pass transition %s on entity %s",
                           trname, entity)